diff --git a/src/crypto/randomx/asm/program_prologue_linux.inc b/src/crypto/randomx/asm/program_prologue_linux.inc
index fcd09fd36..26a305c12 100644
--- a/src/crypto/randomx/asm/program_prologue_linux.inc
+++ b/src/crypto/randomx/asm/program_prologue_linux.inc
@@ -13,12 +13,6 @@
 	mov rbp, qword ptr [rsi]    ;# "mx", "ma"
 	mov rdi, qword ptr [rsi+8]  ;# uint8_t* dataset
 
-	;# dataset prefetch for the first iteration of the main loop
-	mov rax, rbp
-	shr rax, 32
-	and eax, RANDOMX_DATASET_BASE_MASK
-	prefetchnta byte ptr [rdi+rax]
-
 	mov rsi, rdx                ;# uint8_t* scratchpad
 
 	mov rax, rbp
diff --git a/src/crypto/randomx/asm/program_prologue_win64.inc b/src/crypto/randomx/asm/program_prologue_win64.inc
index d70e04911..46a4e9c34 100644
--- a/src/crypto/randomx/asm/program_prologue_win64.inc
+++ b/src/crypto/randomx/asm/program_prologue_win64.inc
@@ -25,12 +25,6 @@
 	mov rbp, qword ptr [rdx]    ;# "mx", "ma"
 	mov rdi, qword ptr [rdx+8]  ;# uint8_t* dataset
 
-	;# dataset prefetch for the first iteration of the main loop
-	mov rax, rbp
-	shr rax, 32
-	and eax, RANDOMX_DATASET_BASE_MASK
-	prefetchnta byte ptr [rdi+rax]
-
 	mov rsi, r8                 ;# uint8_t* scratchpad
 	mov rbx, r9                 ;# loop counter
 
diff --git a/src/crypto/randomx/intrin_portable.h b/src/crypto/randomx/intrin_portable.h
index a24c21ac8..857ea7744 100644
--- a/src/crypto/randomx/intrin_portable.h
+++ b/src/crypto/randomx/intrin_portable.h
@@ -577,8 +577,13 @@ inline void* rx_aligned_alloc(size_t size, size_t align) {
 #   define rx_aligned_free(a) free(a)
 #endif
 
+#ifdef __GNUC__
+#define rx_prefetch_nta(x) __builtin_prefetch((x), 0, 0)
+#define rx_prefetch_t0(x) __builtin_prefetch((x), 0, 3)
+#else
 #define rx_prefetch_nta(x)
 #define rx_prefetch_t0(x)
+#endif
 
 FORCE_INLINE rx_vec_f128 rx_load_vec_f128(const double* pd) {
 	rx_vec_f128 x;
diff --git a/src/crypto/randomx/vm_compiled.cpp b/src/crypto/randomx/vm_compiled.cpp
index 1985e7cae..e3f276bc7 100644
--- a/src/crypto/randomx/vm_compiled.cpp
+++ b/src/crypto/randomx/vm_compiled.cpp
@@ -61,6 +61,17 @@ namespace randomx {
 #		if defined(XMRIG_ARM) || defined(XMRIG_RISCV)
 		memcpy(reg.f, config.eMask, sizeof(config.eMask));
 #		endif
+
+		const uint8_t* p = mem.memory;
+
+		// dataset prefetch for the first iteration of the main loop
+		rx_prefetch_nta(p + (mem.ma & (RandomX_ConfigurationBase::DatasetBaseSize - 64)));
+
+		// dataset prefetch for the second iteration of the main loop (RandomX v2)
+		if (RandomX_CurrentConfig.Tweak_V2_PREFETCH) {
+			rx_prefetch_nta(p + (mem.mx & (RandomX_ConfigurationBase::DatasetBaseSize - 64)));
+		}
+
 		compiler.getProgramFunc()(reg, mem, scratchpad, RandomX_CurrentConfig.ProgramIterations);
 	}